Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5558 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.2632. Min Act: -0.0000

Data Index: 729365 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0511. Min Act: -0.0000

Data Index: 491247 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0090. Min Act: 0.0000

Data Index: 1133522 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1211378 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9016. Min Act: -0.0000

Data Index: 152225 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9023. Min Act: -0.0000

Data Index: 265205 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8853. Min Act: 0.0000

Data Index: 308813 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8351. Min Act: -0.0000

Data Index: 857269 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8382. Min Act: 0.0000

Data Index: 1022149 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8588. Min Act: -0.0000

Data Index: 694414 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8400. Min Act: -0.0000

Data Index: 151139 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8119. Min Act: 0.0000

Data Index: 405351 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8128. Min Act: -0.0000

Data Index: 331695 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8033. Min Act: -0.0000

Data Index: 538741 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.7641. Min Act: -0.0000

Data Index: 129282 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.7640. Min Act: 0.0000

Data Index: 209225 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.7554. Min Act: -0.0000

Data Index: 999951 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.7352. Min Act: -0.0000

Data Index: 366042 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1316366 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.7501. Min Act: -0.0000

Data Index: 252106 (C4 (Web Text))

Max Activating Token Index: 573